A Reservation Method for Multi-agent System Intersection Management with Energy Consumption Considerations

Abstract

A vast number of contemporary studies investigate to resolve traffic congestion in completely autonomous vehicle scenarios. In scenarios when autonomous vehicles approach an intersection at which there are no traffic signals, they are able to drive in a coordinated manner without colliding and minimizing the consumption of fuel or electricity, which results in positive environmental effects. In order to achieve this, a multi-agent management system that includes Vehicle Agents (VAs) and an Intersection Agent (IA) has been used in this paper. In this method, the vehicles will share the area they expect to occupy within the intersection together with their estimated arrival time. The IA, in parallel, arranges reservations on a time-space basis and publicizes the results of reservations to the vehicles. Utilizing this information, individual VAs adjust their speed as efficiently as possible, e.g. reducing their speed or applying an efficient braking strategy, before reaching the intersection zone so that they do not need to stop and can pass through the intersection as quickly as possible. In this paper, the advantages of the proposed system are demonstrated by comparing it with some other types of traffic control systems.